Recipes

Recipes are relatively generic, built-in functionnalities for manipulating a compute graph in Aidge. Some are built with Aidge’s graph matching engine, do not hesitate to have a look at their source code to understand how they work and build similar functionnalities!

🚧 The list of recipes is still growing!

Fuse BatchNorm

Fuse batch normalization with the preceding Conv or FC operator, if possible.

Python

aidge_core.fuse_batchnorm(graph_view: aidge_core.aidge_core.GraphView) → None

Recipe to remove a flatten operator.

Parameters:

graph_view (aidge_core.GraphView) – Graph view on which we want to apply the recipe

C++

void Aidge::fuseBatchNorm(std::shared_ptr<GraphView> graphView)

Fuse :cpp:function:Aidge::BatchNorm with :cpp:function:Aidge::Conv or :cpp:function:Aidge::FC Nodes. Ref: https://nenadmarkus.com/p/fusing-batchnorm-and-conv/.

Parameters:

graphView – Graph view to use graph matching on, in order to apply transformations.

Constant folding

Fold constant operators (like ONNX Simplifier).

C++

void Aidge::constantFolding(std::shared_ptr<GraphView> graph)

Fuse Mul Add

Fuse Mul followed by Add operators into a FC operator.

Python

aidge_core.fuse_mul_add(graph_view: aidge_core.aidge_core.GraphView) → None

Recipe to Fuse MatMul and Add operators into an aidge_core.FC operator.

Parameters:

graph_view (aidge_core.GraphView) – Graph view on which we want to apply the recipe

C++

void Aidge::fuseMulAdd(std::shared_ptr<GraphView> graphView)

Merge MatMul and :cpp:function:Aidge::Add Node into a :cpp:function:Aidge::FC Node.

Parameters:

graphView – Graph view to use graph matching on, in order to apply transformations.

Remove Dropout

Remove Dropout operators.

C++

size_t Aidge::removeDropout(std::shared_ptr<GraphView> graphView)

Remove Dropout Node.

Parameters:

graphView – Graph view to use graph matching on, in order to apply transfomrations.

Returns:

size_t Number of identity nodes removed

Remove Flatten

Remove Flatten operators.

Python

aidge_core.remove_flatten(graph_view: aidge_core.aidge_core.GraphView) → None

Recipe to remove a flatten operator.

Parameters:

graph_view (aidge_core.GraphView) – Graph view on which we want to apply the recipe

C++

void Aidge::removeFlatten(std::shared_ptr<GraphView> graphView)

Remove Flatten before :cpp:function:Aidge::FC Node.

Parameters:

graphView – Graph view to use graph matching on, in order to apply transformations.

Explicit Cast Move

Insert Cast and Move operators where needed (thus removing all implicit data type conversion and backend change data movement).

C++

void Aidge::explicitCastMove(std::shared_ptr<GraphView> graphView)

Add Cast and Move operators where needed to ensure no conversion needs to be done at the Operator level.

Expand meta operators

Expand meta operators, replacing them with their inner graph (flatten the graph).

C++

void Aidge::expandMetaOps(std::shared_ptr<GraphView> graph, bool recursive = false)

Flatten the graph by replacing the meta operators by their micro graph.

Parameters:

recursive – If true, recursively replace meta operators until there is no more meta operator in the graph.